© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75964
    Prev
    Next
    INDEX
    Explanations

    JSON and XML parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liege
    -0.91
    jSON
    -0.86
    toJSON
    -0.86
     jacket
    -0.84
     jackets
    -0.83
    toJson
    -0.81
     VERN
    -0.80
     questionnaires
    -0.79
    Emoji
    -0.79
     ın
    -0.78
    POSITIVE LOGITS
    姹
    0.80
    vska
    0.74
     polypep
    0.74
    昶
    0.74
     Server
    0.72
     Landwir
    0.70
    fstream
    0.70
    PCell
    0.69
     Pretty
    0.69
     European
    0.68
    Activations Density 0.021%

    No Known Activations